create-tech-spec
Skill3 starsChanged 8 days agoMITView on GitHub
Generate a technical specification or design document for a proposed implementation using context from prior research. Includes solution approach, component breakdown (leverage/enhance/build), sequence diagrams, work estimates, and rollout plan. Use when the user wants to create a tech spec, write a design doc, document a proposed solution, or says "tech spec", "design document", or "implementation proposal" after completing research.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- warpdotdev/oz-for-osstheir own version, first seen Oct 8, 2026
- shiggydoodah/skillstheir own version, first seen Aug 6, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- warpdotdev/oz-for-oss★ 313same name
- shiggydoodah/skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- agent-statsSkill
- aristotle-deconstructorSkill
- babysit-prsSkill
- briefingSkill
- code-auditorSkill
- core-editSkill
- create-jira-ticketSkill
- cyrus-tdd-engineerSkill
- doctorSkill
- dotfiles-syncSkill
- forgeSkill
- google-docsSkill
- google-driveSkill
- grill-meSkill
- handoffSkill
- lessons-reviewSkill
- mermaid-diagramsSkill
- metrics-emitSkill
- obligationsSkill
- optimus-plannerSkill
- overlay-initSkill
- performance-reviewSkill
- pr-create-from-commitsSkill
- ranger-reviewerSkill
- record-demoSkill
- review-contextSkill
- review-respondSkill
- scout-reviewerSkill
- self-evaluateSkill
- smart-compactSkill
- smart-statuslineSkill
- swarm-retroSkill
- team-leadSkill
- ticket-pickupSkill
- ticket-swarmSkill
- to-prdSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Before generating output, determine where to save files:
- Distinctive: line 29
Review existing context: - Use findings from prior research/report
- Distinctive: line 32
Generate tech spec: - Use the template below
- Very specific: line 42
Use the template in tech-spec-template.md (in this skill directory).
- Distinctive: line 46
When filling out sections:
- Distinctive: line 50
Section 4.2 Sequence diagrams: Use Mermaid syntax if possible
- Distinctive: line 56
After saving the tech spec locally:
- Very specific: line 69
If the tech spec contains mermaid diagrams that need to be exported as PNG images for Google Docs, use the /mermaid-diagrams skill to …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create Tech Spec
Generate a tech spec using context from a prior /research or /create-report run.
Output Location
Before generating output, determine where to save files:
- Check user prompt — if the user specifies a path, use that (one-time override)
- Check
persist-path.txt— look fordata/persist-path.txtin this skill's directory (resolves via~/.claude/skills/create-tech-spec/data/persist-path.txtor~/.cursor/skills/create-tech-spec/data/persist-path.txt) - If file exists — use the path from it
- If file does not exist — prompt the user:
"Where would you like tech specs saved? Provide an absolute path (e.g.,
~/Desktop/Tech Specs)." - Persist the choice — write to
data/persist-path.txtin this skill's directory
Prerequisites
This skill works best with prior context from research or an existing report. If no prior context exists, prompt the user to provide relevant background or run a codebase exploration first.
Process
- Review existing context - Use findings from prior research/report
- Identify gaps - Determine missing information for the spec
- Ask clarifying questions - Fill in gaps before generating
- Generate tech spec - Use the template below
- Save to desktop - Output as markdown file
Output
Save the tech spec (path from persist-path.txt; see "Output Location" section):
- Filename:
[feature-name]-tech-spec-[YYYY-MM-DD].md
Template
Use the template in tech-spec-template.md (in this skill directory).
Guidance
When filling out sections:
- Section 3.2 Alternatives: Pull from prior research/report analysis
- Section 4.1 Components: Categorize as Leverage (reuse), Enhance (modify), Build (new)
- Section 4.2 Sequence diagrams: Use Mermaid syntax if possible
- Section 6 Work estimates: Provide ranges if uncertain
- Section 8 Rollout plan: Include feature flag strategy per project conventions
Google Docs Integration
After saving the tech spec locally:
- If user mentioned "Google Doc" in prompt → Create immediately without confirmation
- Otherwise → Ask: "Would you like me to create this as a Google Doc?"
If yes:
bash ~/.claude/skills/google-docs/scripts/create_from_markdown.sh "[Feature] Tech Spec - [YYYY-MM-DD]" --file /path/to/spec.mdSee google-docs/integration.md skill for details.
If the tech spec contains mermaid diagrams that need to be exported as PNG images for Google Docs, use the /mermaid-diagrams skill to convert them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.